{"id":"https://openalex.org/W4312695182","doi":"https://doi.org/10.1109/tcsvt.2022.3216663","title":"Multi-Scale Human-Object Interaction Detector","display_name":"Multi-Scale Human-Object Interaction Detector","publication_year":2022,"publication_date":"2022-11-03","ids":{"openalex":"https://openalex.org/W4312695182","doi":"https://doi.org/10.1109/tcsvt.2022.3216663"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2022.3216663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3216663","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031364544","display_name":"Yamin Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yamin Cheng","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-6080-0390","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100376399","display_name":"Zhi Wang","orcid":"https://orcid.org/0000-0002-5462-6178"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Wang","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043425375","display_name":"Wenhan Zhan","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhan Zhan","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0002-1851-7185","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102079217","display_name":"Hancong Duan","orcid":"https://orcid.org/0000-0002-7721-7422"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hancong Duan","raw_affiliation_strings":["School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031364544"],"corresponding_institution_ids":["https://openalex.org/I150229711"],"apc_list":null,"apc_paid":null,"fwci":1.7347,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86101063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"33","issue":"4","first_page":"1827","last_page":"1838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7112759947776794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7023029923439026},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6183241009712219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6182599663734436},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5478267073631287},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.546174168586731},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5173415541648865},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4503841698169708},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.15465745329856873},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12252116203308105},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.06200847029685974}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7112759947776794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7023029923439026},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6183241009712219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6182599663734436},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5478267073631287},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.546174168586731},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5173415541648865},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4503841698169708},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.15465745329856873},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12252116203308105},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.06200847029685974},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2022.3216663","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2022.3216663","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W1551928752","https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2333112450","https://openalex.org/W2531409750","https://openalex.org/W2549139847","https://openalex.org/W2738982359","https://openalex.org/W2740962769","https://openalex.org/W2921869645","https://openalex.org/W2962766617","https://openalex.org/W2963097937","https://openalex.org/W2976818183","https://openalex.org/W2982083293","https://openalex.org/W2994729841","https://openalex.org/W2997150218","https://openalex.org/W3006871679","https://openalex.org/W3009811369","https://openalex.org/W3015356384","https://openalex.org/W3021893287","https://openalex.org/W3034895839","https://openalex.org/W3034934229","https://openalex.org/W3034951775","https://openalex.org/W3035598501","https://openalex.org/W3047999543","https://openalex.org/W3095753865","https://openalex.org/W3096609285","https://openalex.org/W3097802466","https://openalex.org/W3106121867","https://openalex.org/W3107081247","https://openalex.org/W3109754877","https://openalex.org/W3109813419","https://openalex.org/W3119381934","https://openalex.org/W3121523901","https://openalex.org/W3126195189","https://openalex.org/W3131500599","https://openalex.org/W3136792391","https://openalex.org/W3138516171","https://openalex.org/W3139633126","https://openalex.org/W3156811085","https://openalex.org/W3168488421","https://openalex.org/W3170841864","https://openalex.org/W3171169846","https://openalex.org/W3174480456","https://openalex.org/W3179066717","https://openalex.org/W3179869055","https://openalex.org/W3181762391","https://openalex.org/W3195680250","https://openalex.org/W3199093552","https://openalex.org/W3205765769","https://openalex.org/W3206263120","https://openalex.org/W3209102402","https://openalex.org/W3215084804","https://openalex.org/W3216503882","https://openalex.org/W4205432963","https://openalex.org/W4205564931","https://openalex.org/W4214493665","https://openalex.org/W4214588794","https://openalex.org/W4214709605","https://openalex.org/W4229002426","https://openalex.org/W4283716849","https://openalex.org/W4285116117","https://openalex.org/W4297775537","https://openalex.org/W6632922691","https://openalex.org/W6638667902","https://openalex.org/W6737664043","https://openalex.org/W6739901393","https://openalex.org/W6754152559","https://openalex.org/W6769311773","https://openalex.org/W6784094891","https://openalex.org/W6785527955","https://openalex.org/W6788135285","https://openalex.org/W6790690058","https://openalex.org/W6794906783","https://openalex.org/W6796721132","https://openalex.org/W6796814978","https://openalex.org/W6802010497","https://openalex.org/W6802599522"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2366906938","https://openalex.org/W2349391998","https://openalex.org/W4205655149","https://openalex.org/W2183306018","https://openalex.org/W2000775715","https://openalex.org/W2549990292","https://openalex.org/W2345479200","https://openalex.org/W2951819827","https://openalex.org/W2849310602"],"abstract_inverted_index":{"Transformers":[0],"are":[1,47],"transforming":[2],"the":[3,22,48,90,98,102,109,118,144,156,178],"landscape":[4],"of":[5,82,87,104,117,126,181],"computer":[6],"vision,":[7],"especially":[8],"for":[9,28,40,53],"image-level":[10,54],"recognition":[11,55],"and":[12,46,56,77,150,176,186],"instance-level":[13,57],"detection":[14,18,79,158],"tasks.":[15],"Human-object":[16],"interaction":[17,30,68],"transformer":[19,51,92,140],"(HOI-TR)":[20],"is":[21],"first":[23,49],"transformer-based":[24,65],"end-to-end":[25],"learning":[26],"system":[27],"human-object":[29,67],"(HOI)":[31],"detection;":[32],"vision":[33,91],"transformers":[34],"build":[35,63],"a":[36,64,71],"simple":[37],"multi-stage":[38],"structure":[39],"multi-scale":[41,66],"representation":[42],"with":[43,124],"single-scale":[44,110],"patch":[45,111,134],"patch-based":[50],"architecture":[52,95],"detection.":[58],"In":[59],"this":[60],"paper,":[61],"we":[62],"detector":[69],"(MHOI),":[70],"novel":[72],"method":[73],"to":[74,96,108,154],"integrate":[75],"Vision":[76],"HOI":[78,157],"Transformer,":[80],"instead":[81],"directly":[83],"incorporating":[84],"two":[85],"types":[86],"transformers,":[88],"since":[89],"lacks":[93],"hierarchical":[94],"handle":[97],"large":[99],"variations":[100],"in":[101],"scale":[103],"visual":[105],"entities":[106],"due":[107],"partitioning.":[112],"Specifically,":[113],"MHOI":[114],"embeds":[115],"features":[116],"same":[119],"size":[120],"(i.e.,":[121],"sequence":[122],"length)":[123],"patches":[125],"variable":[127],"scales":[128],"simultaneously":[129],"by":[130],"utilizing":[131],"overlapping":[132],"convolutional":[133],"embedding,":[135],"then":[136],"introduces":[137],"an":[138],"efficient":[139],"decoder":[141],"that":[142,167],"designs":[143],"query":[145],"based":[146],"on":[147,163,184,189],"anchor":[148],"points":[149],"essential":[151],"auxiliary":[152],"techniques":[153],"boost":[155],"performance.":[159],"Numerically,":[160],"extensive":[161],"experiments":[162],"several":[164],"benchmarks":[165],"demonstrate":[166],"our":[168],"proposed":[169],"framework":[170],"outperforms":[171],"prior":[172],"existing":[173],"methods":[174],"coherently":[175],"achieves":[177],"impressive":[179],"performance":[180],"29.67":[182],"mAP":[183,188],"HICO-DET":[185],"58.7":[187],"V-COCO,":[190],"respectively.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}